Gnosis LLM Self Awareness

Enable frozen LLMs to predict their own correctness by decoding signals from internal hidden states and attention patterns, achieving reliable self-verification without external judges—adding only 5M parameters while reducing inference cost and improving calibration.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 12ffbce4a4

Frequently asked questions

npx get-skill add adu2021/gnosis-llm-self-awareness